Mapping and Compressing a Convolutional Neural Network through a Multilayer Network

This paper falls in the context of the interpretability of the internal structure of deep learning architectures. In particular, we propose an approach to map a Convolutional Neural Network (CNN) into a multilayer network. Next, to show how such a mapping helps to better understand the CNN, we propose a technique for compressing it. This technique detects if there are convolutional layers that can be removed without reducing the performance too much and, if so, removes them. In this way, we obtain lighter and faster CNN models that can be easily employed in any scenario.